NLPGD

Preface

Employees are the heart and soul of a business. Their actions and performance are what drive the profitability of a business and it’s ability to maximize shareholder value. In the following document, we look to address the following question:

Is there a relationship between employee sentiment and excess returns?

By building a webscraping program and applying it to GlassDoor, we were able to compile a comprehensive of employee reviews across a va of companies:

  • ExxonMobil (XOM)
  • Chevron (CVX)
  • Shell (SHEL)
  • BP (BP)

For context on the analysis that occurs below, here is a chart that represents their respective share prices from the last 10 years:

We wanted to select companies that all operate in the same industry and differ by market cap. This ensures that our analysis truly represents differentiating factors in relation to excess returns.

Firstly, we needed to make sense of all the reviews and how best to compile and analyze them. Natural Language processing is the computational analysis of language and speech. This essentially analyzes words and phrases and rates them numerically or categorically based off of the emotion and message they are conveying. Here is a short description of the two methods we applied:

  • Bing: A dataset of 6,786 words with binary positive and negative sentiment scores
word sentiment
2-faces negative
abnormal negative
abolish negative
zest positive
zippy positive
zombie negative
  • Afinn: A dataset of 2477 words with scores ranging from -5 to 5:
word value
breathtaking 5
superb 5
thrilled 5
amazing 4
awesome 4
brilliant 4

We also utilized the star ratings that employees leave whenever a review is posted (ranging from 1 star to 5 stars). To organize our data into workable metrics. We used individual words instead of ngrams (collection of words or short sentences) as the bulk of the reviews are short and sometimes contain only one word. To summarize, we opted for the following:

  • Grouped reviews into monthly, quarterly and annual bins.
  • Bing was organized into percentage of reviews that were deemed positive and averaged over monthly, quarterly and annually.
  • Afinn was organized into average total score over monthly, quarterly and annually.
  • Star ratings were averaged over monthly, quarterly and annually.

Here are some visuals that are separated by company, depicting how these various metrics change through time. All charts use monthly data to help tell the story:

# A tibble: 6 × 4
  date       Company word     value
  <date>     <chr>   <chr>    <dbl>
1 2018-01-09 bp      terrible    -3
2 2018-01-09 bp      terrible    -3
3 2018-01-15 bp      negative    -2
4 2018-01-10 bp      good         3
5 2018-01-26 bp      best         3
6 2018-01-10 bp      great        3

Alpha Analysis

  • Using CAPM, Alphas were calculated annually for each individual stock

    • 1 Year Beta
    • S&P500 utilized as a proxy for market return

  • Annual Alphas were regressed annually against the preceding year’s average review ratings and sentiment, as defined by the Affin dictionary.

    • Bing NLP excluded due to model multicollinearity

  • Model fit was poor for all four companies

  • Alpha between the four firms w

Characteristic Chevron BP ExxonMobil Shell
Beta 95% CI1 p-value Beta 95% CI1 p-value Beta 95% CI1 p-value Beta 95% CI1 p-value
mean_rating -2.3 -4.6, -0.10 0.043 0.91 -1.2, 3.0 0.3 -1.7 -4.4, 0.94 0.2 -1.2 -4.1, 1.6 0.3
sentiment 1.5 0.14, 2.8 0.036 -0.23 -2.0, 1.6 0.8 0.46 -1.9, 2.8 0.7 1.5 -1.5, 4.5 0.3
1 CI = Confidence Interval

Portfolio-based Analysis

Two portfolios of our selected companies were created

  • Portflio 1: Naive equally-weighted portfolio
    • Rebalanced yearly based upon the prior years closing price
  • Portfolio 2: Optimized portfolio utilizing three sentiment indicators
    • Generated weights utilizing a combination the input indicators
    • Optimization process to determine the ideal relative sentiment mix
      • Training window: 2014-2021
    • Rebalanced annually using an aggregation sentiment data from the prior year
      • Sentiment is treated on a absolute basis as opposed to on a relative basis to prior years
      • Companies are proportional de-weighted in cases of ‘review slippage’ relative to their peers
        • No additionally compounds are included for +/- review drift
Optimized Weights
Return Variance Positive Prop. Rating Sentiment Portfolio
0.4329687 0.0731107 1 0 0 Optimized Sentiment-based
0.4282956 0.0738970 NA NA NA Naive